Código abierto
1635
154
COMPASS: Routing via Capability-Oriented Model Profiling with Adaptive Search, Selection, and Tool Use
LLM routing aims to select a capable model at low cost, but specialized routers can require updates as models and tasks change. We propose COMPASS, an agentic router in which an LLM follows a routing recipe, gathers performance and cost evidence through tools, and optionally inspects candidate answers before selecting a model. Our evaluations on LLMRouterBench and DeepSWE show that agentic routing can improve accuracy and lower model-call cost relative to specialized and trained routing baselines, without routing-specific training. On LLMRouterBench, COMPASS reaches 69.85% accuracy at \139.57, compared with RLCascadeRouter's 69.14% at \180.22. On DeepSWE under fixed five-fold cross-validation, it reaches 78.1% at \215, compared with 74.1% at \500 for the best single model. COMPASS also supports routing across benchmarks and adapts to an expanded model pool by reading new evaluation records, without changing the router's weights or prompt.
TerraNostra-Bench: Benchmarking Spatial Downscaling and Temporal Rollout for Global 1-km Land-Use Reconstruction
Uncertainty in the terrestrial carbon cycle remains a major constraint in climate projections, partly due to imperfect land surface representations in Earth system models. We propose a data-driven framework for high-resolution land-use reconstruction, treated as a semantic-segmentation task, that combines coarse-resolution scenario data and climate classification with static geophysical features to produce annual land-use maps at 1 km resolution. We introduce TerraNostra-Bench, a change-aware evaluation protocol that separates spatial downscaling from autoregressive temporal rollout and scores models on the rare land-use-change pixels rather than the dominant static background. Using it, we compare convolutional (U-Net) and transformer (Swin) backbones in autoregressive and non-autoregressive schemes against persistence, linear, and shallow convolutional baselines. The autoregressive prior is the most informative input yet accumulates error over long rollouts: autoregressive models lose 5.7-7.2 accuracy points over 13 years, against 2.2-2.8 for non-autoregressive models. This trade-off is governed by the autoregressive choice rather than the backbone. It can be tuned by an inference-time prior-trust threshold that requires no retraining and by the training-time weighting of reconstruction and change objectives; the two levers trace complementary frontiers, with calibration recovering up to 10 accuracy points while keeping change sensitivity above the persistence floor. Extrapolating beyond the training window, backward to 1955-1959 and forward to 2015-2019 under scenario forcing, the models retain most of their in-window skill and show the same trade-off, indicating it is intrinsic to the design. This work provides the methodological foundation and evaluation surface for a forthcoming temporally continuous land-use product.
GRADUS: Discovering and Recovering Agent Lessons from the Environment's Latent Syllabus
Training LLM agents for policy-constrained tool environments, such as an airline backend with booking, refund, and cancellation policies, requires tasks that exercise the environment's rules individually and in combination. Existing synthesis pipelines let a model propose tasks and retain only those it immediately solves, biasing training data toward easier behaviors. We introduce Gradus (Graded Rungs of Ascending Difficulty from an Underlying System), which decouples what a task should teach from the concrete task and solution used to teach it. Without seed tasks, Gradus treats a fixed environment as a latent syllabus, extracting guarded behavioral operators that capture how actions depend on current conditions and how their effects reshape subsequent decisions. It composes these operators into increasingly demanding tasks while using corpus-level feedback to target missing outcome combinations. Crucially, Gradus jointly calibrates tasks and solutions against the environment: execution feedback identifies which side to refine while preserving the intended behavioral requirements. Verification thus becomes a recovery signal rather than a terminal filter, coupling coverage-guided exploration with the preservation of difficult examples. From off-the-shelf backbones, the resulting curriculum lifts a 30B model from 59% to 89% on τ^2-Bench and from 47% to 83% on CAR-Bench with an Opus 4.5 proposer, and to 76% and 62%, respectively, with an open-weight Qwen3-235B proposer. These results show the value of jointly controlling which behaviors are explored and which survive into verified training data.
AC/DC on a Budget - Alternating Sparse Phases
State-of-the-art neural network sparsification relies on alternating dense and sparse training phases. While computationally expensive, dense phases are critical for performance. Our empirical analysis reveals the mechanics behind this gain: upon reintroduction, previously masked parameters receive disproportionately large gradients that drive essential mask rewiring and parameter sign-flipping. Building on these insights, we optimize the performance-to-FLOPs Pareto frontier through three innovations: (1) zero-initializing masked parameters during dense phases to promote relevant sign flips, (2) shortening dense phases, and (3) replacing the dense phase entirely with a sparse rewiring phase that updates only the active mask and a small, high-gradient fraction of out-of-mask weights. Evaluated on CIFAR100 and ImageNet, our variant ARC (Alternating Rewiring Compression) matches baseline AC/DC performance at a fraction of the computational cost, establishing a superior performance-to-FLOPs frontier also compared to standard sparse-to-sparse algorithms. Experiments with GPT-2 on OpenWebText further show improvements in validation perplexity and average zero-shot performance
Spain-Based Startups Advance Regional Innovation With Barcelona Supercomputing Center
The Barcelona Supercomputing Center (BSC)’s AI Factory Accelerator Programme, now in full operation following a pilot initiative, gives startups access to sovereign compute, technical support and training to support innovation across industries. Many of these companies are also members of the NVIDIA Inception program for cutting-edge startups — and as of today, access to some […]
Amazon SageMaker JumpStart: 2026 year-to-date in review
Amazon SageMaker JumpStart onboarded over 100 new models from 30 providers in the first three quarters of 2026. This recap covers the model-onboarding highlights and JumpStart enhancements, including the simplified Model Hub, pre-configured deployment options, and Hugging Face deep link integration.
Hackers hit AI coding tool OpenCode, running up charges on users’ AI accounts
OpenCode is an open-source AI coding agent that's become a popular alternative to Claude Code and Cursor. But hackers got into part of its online…
Tenstorrent hits $6.2B valuation to scale open-weight AI chips
After drawing acquisition interest earlier this year, the Nvidia challenger raised $1.5 billion to remain independent.
WeAct: Dynamic Weight Switching as Agent Actions
Long-horizon agents must learn heterogeneous capabilities from interleaved trajectories. Updating shared parameters to learn new capabilities can degrade previously acquired ones, resulting in catastrophic forgetting. As a trajectory unfolds, different stages may require different capabilities, yet conventional joint training and static adapter merging maintain a fixed parameter configuration throughout execution. We introduce WeAct (Weight-level Internal Actions), which trains independent capability-specific LoRA adapters over a frozen backbone and adds adapter selection to the agent's action space. These internal actions use the model's native tool-calling interface for on-demand capability composition in a shared context. Across eight deep-research benchmarks, Qwen3-32B with WeAct improves average accuracy by 6.2% relative to full fine-tuning counterparts despite using less compute, and by 27.5% relative to the strongest static LoRA-merging method. WeAct also supports modular continual adaptation, by adding a new code computation adapter to expand the agent's capabilities and updating the existing writing adapter to improve report quality. Both updates leave the backbone and other adapters unchanged, supporting modular continual adaptation in agents.
AnyGoal: On World Model Generalization Beyond Expert Rollouts
The goal of a world model is to capture the dynamics of an environment. This has the great appeal that it allows agents to plan and simulate a course of actions with the help of a world model. For these uses to be reliable, however, the learned dynamics must behave well beyond the specific state-action combinations observed in expert rollouts. Despite this, the relationship between data coverage, dynamics generalization, and downstream planning performance remains underexplored. We study this relationship through the lens of compositional generalization: can a world model recombine familiar state and action factors into valid dynamics? To answer this, we introduce AnyGoal, a benchmark of goal-shifted task variants built from widely used world-model environments, together with an open-source library. Each task is designed to be within reach of a world model that has learned the underlying dynamics: individual state factors and actions remain within their training support, but their combinations are underrepresented in expert trajectories. Across multiple environments and world model families, we find that current models consistently exhibit failures under these recombinations. By examining dynamics and representation failures across model families, interaction regimes, and evaluation metrics, we study where current world models generalize and where challenges remain for goal-shifted prediction and planning. Together, this framework, benchmark, and analysis provide a basis for evaluating progress toward world models that generalize to new planning tasks.
Kronecker Delta Rule for Long Context Linear Attention
We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision mechanism that corrects targeted associations while modifying the memory only along a single direction in matrix space. This minimally invasive memory revision reduces interference with previously stored information compared with delta-rule updates, making it particularly well suited for long-context language modeling. The resulting memory dynamics can be mathematically described as a Markov chain that converges to a steady-state distribution, while the expected norm of the memory matrix remains uniformly bounded throughout the entire input sequence. Hence, KronLSTM ensures stable memory dynamics without requiring additional normalization and stabilization mechanisms for the memory state. Experiments show that KronLSTM is competitive with, and often outperforms, existing linear attention architectures, including models of the (Gated) DeltaNet family, with particularly strong performance on long context benchmarks. These results establish the Kronecker Delta Rule as an effective and analytically tractable foundation for stable associative memory in recurrent linear attention architectures. Our code (https://github.com/NX-AI/KronLSTM) and models (https://huggingface.co/collections/NX-AI/kronlstm) are open-source.
Competing Learning in Hybrid Architectures
Many modern language models have adopted hybrid architectures that incorporate both linear-time recurrence and softmax attention. Modern recurrence layers provide a highly expressive mixing mechanism while ensuring high throughput by compressing contextual information into a fixed-size state, but underperform softmax attention in contextual information retrieval. In this paper, we reveal a Competing Learning phenomenon where different kinds of mixers compete to learn the same function, and when any layer learns a function, it suppresses the corresponding learning signal for other layers. Layer attribution analysis reveals that under typical data distributions, modern recurrence learns retrieval functions faster than softmax attention, causing attention to fail to learn retrieval in most cases. Stopping weight updates in recurrence in the middle of training helps attention learn retrieval. Based on these results, we propose a staged training procedure for pre-training hybrid architectures on natural language. Empirical results on models up to 1B parameters show that our method results in substantial improvement in language modeling loss, common-sense reasoning, as well as a wide range of retrieval-related tasks across different context lengths.
Agent World Model in the Wild: Computer-Use Agent Environment Synthesis
Agent learning is shifting from learning from human data toward learning through interaction with the world. However, scaling such learning directly in real-world computer systems is challenging and can introduce substantial security risks. We therefore propose Agent World Model in the Wild (WildAWM), a scalable pipeline for synthesizing controllable environments and tasks for training general computer-use agents (CUAs). Whereas existing approaches typically specialize in a single agent interaction interface, we construct executable environments that jointly support graphical user interfaces, model context protocol services, and command-line interfaces, allowing agents to flexibly combine visual interaction, tool use, and code execution. WildAWM is entirely powered by open-source models, demonstrating that high-quality computer-use environments can be generated without proprietary frontier models. Beyond environments, we address three recurring challenges in task synthesis: ensuring solvability, maintaining sufficient difficulty, and producing reliable verifiers, by introducing execution-based quality gates that combine heterogeneous agent rollouts, cross-judge consistency checks, and counterfactual probes of judgment robustness. The resulting pipeline synthesizes 341 long-horizon environment-task pairs that can require over 100 agent steps to solve and remain challenging even for frontier models, with GPT-6-Astra solving only 60% of them. We train two Qwen models of different sizes exclusively in these synthetic worlds. Both models achieve substantial gains across 8 out-of-distribution benchmarks spanning web, claw, and computer-use agents, demonstrating that learning in WildAWM's synthesized worlds generalizes broadly to unseen computer-use tasks. The code is publicly available at https://github.com/MSR-Orchard/WildAWM.
KEEP-Bench: Evaluating Evidence Preservation in Context Compression
Context compression improves long-context efficiency but may introduce faithfulness issues through an information bottleneck. Existing evaluations rely on QA metrics, but a reader can still answer correctly from an unfaithful compression, so these metrics underestimate such loss. To bridge this gap, we introduce KEEP-Bench, a diagnostic benchmark that directly assesses compression faithfulness with 4,102 cases across three challenging settings that require keeping evidence for plausible reference resolutions, explicit qualifiers, and minority perspectives. Experiments show that even with tailored prompting, the strongest models remain unreliable: despite context windows exceeding 100K tokens and inputs averaging only 3.1K tokens, the best open-weight model (31B) preserves all required evidence in only 66.8% of cases, and the best proprietary model in only 61.6%. Performance also varies sharply across evidence structures, so conclusions from limited structures may be biased. We further introduce a metric, Evidence Preservation Return (EPR), to relate evidence recall to inference FLOPs, and find that it peaks at moderate scales (4B-8B), where recall remains low. Additional output budget mainly benefits already strong models and widens capability gaps, yet the stronger preservation of these models comes at a steep computational cost. These findings highlight the importance for future work to investigate compressors with strong information preservation under a small computation budget, rather than relying on a large output budget or model scaling.
Learning to Refer: Inference-Time Collaboration in Decentralized Federated Learning
In decentralized federated learning, heterogeneous clients may develop complementary expertise, yet each query is typically evaluated only by the client where it arrives. To exploit this distributed expertise without global coordination, we formulate inference-time collaboration as budgeted local expert referral, a graph-constrained routing process in which a query can move only between neighboring clients and only visited clients contribute to its final prediction. EdgeDRM implements this framework by learning a density-based routing potential for each client: differences between neighboring potentials provide the comparisons used to select successive referrals, while local task models generate predictions that are aggregated along the resulting route. Both training and inference are decentralized, using only neighbor-local information without a central router or graph-wide client scoring. We establish estimation guarantees for the learned comparisons and characterize how local improvement and graph structure govern prior-weighted density gains from referral. Experiments on benchmark and real-world medical data show that EdgeDRM outperforms graph-matched decentralized baselines in most settings, with the clearest benefits under sparse connectivity.
LG-Bench: A Graph-Structured Evaluation Benchmark for Life Sciences
Traditional evaluation benchmarks reduce inherently interconnected scientific knowledge in life sciences into flat lists of questions, disregarding the underlying topological structure of the knowledge. We introduce, the first graph-structured benchmark for life sciences, featuring over 10,000 high-quality multiple-choice questions across medicine, biology, and chemistry. Our approach constructs a weighted evaluation graph using bidirectional matching and semantic similarity algorithms, where nodes represent questions and edge weights capture their semantic relationships. Leveraging this graph topology, we design two novel evaluation metrics. The Global Coherence Score (GCS) measures a model's consistency within semantically related neighborhoods, while Knowledge Balance Score (KBS) analyzes how model errors are distributed across the graph to reveal conceptual blind spots. LG-Bench facilitates fine-grained comparison of LLMs by surfacing differences in conceptual coherence and patterns of knowledge organization across models. Our framework shifts the evaluation paradigm from flat accuracy metrics to structure-aware analysis, offering a new lens for diagnosing and improving LLM performance in the life sciences domain.
HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs
Harness development plays a crucial role in building capable AI agents. Recent approaches improve harnesses through recursive self-improvement (RSI), but their performance gains often come with higher execution costs. We introduce HarnessPro, a label-free method for evolving harnesses to improve task performance while reducing execution cost. In this setting, candidate harnesses are evaluated using LLM-generated tests without access to ground-truth solutions or official tests. Specialized agents diagnose execution trajectories, plan updates with different performance-cost priorities, and implement them as candidate harnesses. Rather than returning a single harness, HarnessPro uses normalized weighted squared-distance selection to provide cost-focused (lite), balanced (medium), and performance-focused (heavy) harnesses for different deployment budgets. Selected harnesses enter the next iteration, where execution feedback guides further updates. Our experiments cover Terminal-Bench 2, SWE-Bench Pro, and ProgramBench, using GPT-5.5 with Codex and GLM-5.2 with Claude Code. Across these benchmarks using GPT-5.5 with Codex, the heavy mode of HarnessPro achieves an average pass-rate gain of 2.0 percentage points and an average per-task cost reduction of 26.1% relative to RHO. This advantage also holds when using GLM-5.2 with Claude Code. Code is available at https://github.com/pzs19/HarnessPro
TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning
Expert human readers process large inputs (e.g., code repositories and long documents) by skimming to closely read only what matters. On the other hand, language models process all input tokens through each model layer, resulting in significant processing costs for long-context inputs. We introduce TokenGate, a small, drop-in component that extends existing trained models to enable end-to-end learnable token pruning over long-context inputs for fast and memory-efficient prefill. To enable end-to-end learning despite the non-differentiable top-K operator for token pruning, we introduce token-gated attention, a mechanism inspired by Mixture-of-Experts that re-weights attention logits using token importance scores. Across diverse tasks, TokenGate achieves 1.4-11.3faster time-to-first token (TTFT) and 1.5-3.4lower peak memory at no accuracy degradation for prefill in transformers. Compared to the best-performing prior methods for token-pruning, TokenGate gives up to 6.4faster prefill and 2lower peak memory. TokenGate natively extends both standard transformers (e.g., Qwen3) and hybrid-attention models (e.g., Qwen3.5) with simple lightweight adaptation comparable to standard parameter-efficient fine-tuning. We make our code available at: https://github.com/tokengate-models/TokenGate.